The New Primitives: Building AI-Native Software
Official Schedule Context
- Date/time: 2026-06-29 · 10:45am-11:05am
- Track/room: Voice & Realtime AI · Track 6
- Speaker(s): Kwindla Kramer
- Session type/status: session · confirmed
Official Description
In the future, every piece of software with a human-facing surface will be built from new, LLM-
centric primitives. (Just like every piece of software today has networking, threads/async routines,
UI on top of some flavor of Model/View/Controller abstractions, etc.) We're just starting to invent
these new primitives. The list, though, will definitely include: 1. Subagents - multiple inference
loops, multiple models, async tool calls 2. Very long context - memory + episodic human interactions
over a long period of time, structured data input (not just output), progressive skills/context
loading, graceful compaction & summarization 3. dynamic user interface generation / user interfaces
driven by LLM inference 4. conversational voice input
Related YouTube Video
Your realtime AI is ngmi — Sean DuBois (OpenAI), Kwindla Kramer (Daily) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.
People
Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.
Supporting Slides
- youtube E71YtNbCFXY slides — extracted from the related public AI Engineer video.
Slide Evidence
- Slide-only cropped deck: youtube E71YtNbCFXY dense slides (1 viable slide images).
- Related slide/OCR pages:
- youtube E71YtNbCFXY dense slides
- youtube E71YtNbCFXY reconstructed slides
- youtube E71YtNbCFXY slides
- Slide-derived terms:
code,voice-to-voice,latency,websockets,pipecat,atency,lines,awws,graphite,windsurf,mongobb,mdaily,augment,workos,milliseconds,typical,during,human